Skip to content

mm: COW fixes part 3: reliable GUP R/W FOLL_GET of anonymous pages

David Hildenbrand linux-arm-kernel linux-mm linux-s390 linuxppc-dev lkml 2 versions – In review

Get series with b4
b4 am [email protected]

Versions newest first · linked by author and title

  1. v2 Latest8 patches 14 repliesIn review 7 of 8 applied
  2. v17 patches 24 repliesSuperseded

v2 -> v3 from the cover letter

* Rebased and retested
* "arm64/pgtable: support __HAVE_ARCH_PTE_SWP_EXCLUSIVE" -> Add RB and a comment to the patch description
* "s390/pgtable: cleanup description of swp pte layout" -> Added
* "s390/pgtable: support __HAVE_ARCH_PTE_SWP_EXCLUSIVE" -> Use new set_pte_bit()/clear_pte_bit()
-> Fixups comments/patch description

Patches in v2 7 of 8 applied

#Subject and filesSizeRepliesApplied
1/8mm/swap: remember PG_anon_exclusive via a swp pte bitinclude/linux/pgtable.h include/linux/swapops.h mm/memory.c +2 more+105 -138 repliesApplied
2/8mm/debug_vm_pgtable: add tests for __HAVE_ARCH_PTE_SWP_EXCLUSIVEmm/debug_vm_pgtable.c+15 -01 replyApplied
3/8x86/pgtable: support __HAVE_ARCH_PTE_SWP_EXCLUSIVEarch/x86/include/asm/pgtable.h arch/x86/include/asm/pgtable_64.h arch/x86/include/asm/pgtable_types.h+24 -11 reply
4/8arm64/pgtable: support __HAVE_ARCH_PTE_SWP_EXCLUSIVEarch/arm64/include/asm/pgtable-prot.h arch/arm64/include/asm/pgtable.h+21 -30 repliesApplied
5/8s390/pgtable: cleanup description of swp pte layoutarch/s390/include/asm/pgtable.h+8 -91 replyApplied
6/8s390/pgtable: support __HAVE_ARCH_PTE_SWP_EXCLUSIVEarch/s390/include/asm/pgtable.h+21 -21 replyApplied
7/8powerpc/pgtable: remove _PAGE_BIT_SWAP_TYPE for book3sarch/powerpc/include/asm/book3s/64/pgtable.h+5 -72 repliesApplied
8/8powerpc/pgtable: support __HAVE_ARCH_PTE_SWP_EXCLUSIVE for book3sarch/powerpc/include/asm/book3s/64/pgtable.h+20 -10 repliesApplied

Reviews trailers per patch

5 of 8 patches have a Reviewed-by or Acked-by.

PatchCatalin MarinasGerald SchaeferVlastimil Babka
1/8A-b
2/8A-b
3/8
4/8R-b
5/8R-b
6/8R-b
7/8
8/8

Trailers given in replies are filled; those carried in the patches from earlier versions are outlined with dashes. Scroll the table sideways for all 3 reviewers.

Read the v2 thread

Cover letter [PATCH v2 0/8] mm: COW fixes part 3: reliable GUP R/W FOLL_GET of anonymous pages

More information on the general COW issues can be found at [2]. This series is based on latest linus/master and [1]:
[PATCH v3 00/16] mm: COW fixes part 2: reliable GUP pins of anonymous pages

v2 is located at:
https://github.com/davidhildenbrand/linux/tree/cow_fixes_part_3_v2

This series fixes memory corruptions when a GUP R/W reference (FOLL_WRITE | FOLL_GET) was taken on an anonymous page and COW logic fails to detect exclusivity of the page to then replacing the anonymous page by a copy in the page table: The GUP reference lost synchronicity with the pages mapped into the page tables. This series focuses on x86, arm64, s390x and ppc64/book3s -- other architectures are fairly easy to support by implementing __HAVE_ARCH_PTE_SWP_EXCLUSIVE.

This primarily fixes the O_DIRECT memory corruptions that can happen on concurrent swapout, whereby we lose DMA reads to a page (modifying the user page by writing to it).

O_DIRECT currently uses FOLL_GET for short-term (!FOLL_LONGTERM) DMA from/to a user page. In the long run, we want to convert it to properly use FOLL_PIN, and John is working on it, but that might take a while and might not be easy to backport. In the meantime, let's restore what used to work before we started modifying our COW logic: make R/W FOLL_GET references reliable as long as there is no fork() after GUP involved.

This is just the natural follow-up of part 2, that will also further reduce "wrong COW" on the swapin path, for example, when we cannot remove a page from the swapcache due to concurrent writeback, or if we have two threads faulting on the same swapped-out page. Fixing O_DIRECT is just a nice side-product

This issue, including other related COW issues, has been summarized in [3] under 2):
"
2. Intra Process Memory Corruptions due to Wrong COW (FOLL_GET)

It was discovered that we can create a memory corruption by reading a file via O_DIRECT to a part (e.g., first 512 bytes) of a page, concurrently writing to an unrelated part (e.g., last byte) of the same page, and concurrently write-protecting the page via clear_refs SOFTDIRTY tracking [6].

For the reproducer, the issue is that O_DIRECT grabs a reference of the target page (via FOLL_GET) and clear_refs write-protects the relevant page table entry. On successive write access to the page from the process itself, we wrongly COW the page when resolving the write fault, resulting in a loss of synchronicity and consequently a memory corruption.

While some people might think that using clear_refs in this combination is a corner cases, it turns out to be a more generic problem unfortunately.

For example, it was just recently discovered that we can similarly create a memory corruption without clear_refs, simply by concurrently swapping out the buffer pages [7]. Note that we nowadays even use the swap infrastructure in Linux without an actual swap disk/partition: the prime example is zram which is enabled as default under Fedora [10].

The root issue is that a write-fault on a page that has additional references results in a COW and thereby a loss of synchronicity and consequently a memory corruption if two parties believe they are referencing the same page.
"

We don't particularly care about R/O FOLL_GET references: they were never reliable and O_DIRECT doesn't expect to observe modifications from a page after DMA was started.

Note that:
* this only fixes the issue on x86, arm64, s390x and ppc64/book3s ("enterprise architectures"). Other architectures have to implement __HAVE_ARCH_PTE_SWP_EXCLUSIVE to achieve the same.
* this does *not * consider any kind of fork() after taking the reference:
fork() after GUP never worked reliably with FOLL_GET.
* Not losing PG_anon_exclusive during swapout was the last remaining piece. KSM already makes sure that there are no other references on a page before considering it for sharing. Page migration maintains PG_anon_exclusive and simply fails when there are additional references (freezing the refcount fails). Only swapout code dropped the PG_anon_exclusive flag because it requires more work to remember + restore it.

With this series in place, most COW issues of [3] are fixed on said architectures. Other architectures can implement __HAVE_ARCH_PTE_SWP_EXCLUSIVE fairly easily.

[1] https://lkml.kernel.org/r/[email protected]
[2] https://lkml.kernel.org/r/[email protected]
[3] https://lore.kernel.org/r/[email protected]

v2 -> v3:
* Rebased and retested
* "arm64/pgtable: support __HAVE_ARCH_PTE_SWP_EXCLUSIVE" -> Add RB and a comment to the patch description
* "s390/pgtable: cleanup description of swp pte layout" -> Added
* "s390/pgtable: support __HAVE_ARCH_PTE_SWP_EXCLUSIVE" -> Use new set_pte_bit()/clear_pte_bit()
-> Fixups comments/patch description

David Hildenbrand (8):
mm/swap: remember PG_anon_exclusive via a swp pte bit mm/debug_vm_pgtable: add tests for __HAVE_ARCH_PTE_SWP_EXCLUSIVE x86/pgtable: support __HAVE_ARCH_PTE_SWP_EXCLUSIVE arm64/pgtable: support __HAVE_ARCH_PTE_SWP_EXCLUSIVE s390/pgtable: cleanup description of swp pte layout s390/pgtable: support __HAVE_ARCH_PTE_SWP_EXCLUSIVE powerpc/pgtable: remove _PAGE_BIT_SWAP_TYPE for book3s powerpc/pgtable: support __HAVE_ARCH_PTE_SWP_EXCLUSIVE for book3s

 arch/arm64/include/asm/pgtable-prot.h        |  1 +
 arch/arm64/include/asm/pgtable.h             | 23 ++++++--
 arch/powerpc/include/asm/book3s/64/pgtable.h | 31 ++++++++---
 arch/s390/include/asm/pgtable.h              | 36 +++++++++----
 arch/x86/include/asm/pgtable.h               | 16 ++++++
 arch/x86/include/asm/pgtable_64.h            |  4 +-
 arch/x86/include/asm/pgtable_types.h         |  5 ++
 include/linux/pgtable.h                      | 29 +++++++++++
 include/linux/swapops.h                      |  2 +
 mm/debug_vm_pgtable.c                        | 15 ++++++
 mm/memory.c                                  | 55 ++++++++++++++++++--
 mm/rmap.c                                    | 19 ++++---
 mm/swapfile.c                                | 13 ++++-
 13 files changed, 216 insertions(+), 33 deletions(-)
Signature · 1 line
2.35.1